The Elsmar Cove Business Systems and Standards Discussion Forums How to determine the values of k1, k2, k3 in Gage R&R
 Forum User Name Keep Me Logged In Password
 Register Photo Albums Blogs FAQ Registered Visitors Social Groups Calendar Search Today's Posts Mark Forums Read

 Elsmar Cove Forum Visitor Notice(s)

How to determine the values of k1, k2, k3 in Gage R&R - Page 2

 Elsmar XML RSS Feed Monitor the Elsmar Forum Sponsor Links Courtesy Quick Links Links Elsmar Cove visitors will find useful in the quest for knowledge and support: International Standards Bodies - World Wide Standards Bodies International Organization for Standardization - ISO Standards and Information Quality Digest

 Thread Tools Search this Thread Rate Thread Content Display Modes
Post Number #9
12th December 2007, 09:22 PM
 Alex.G Total Posts: 9
Re: How to determine the values of k1, k2, k3 in Gage R&R

I still don't clearly see where the problem is from, PV or TV?
I review my spreadsheet and I tried to insert the values from the MSA reference manual 3rd edition p 113, with my spreadsheet I get exactly the same value as p114, my excel is wrong or not? did they made a mistake in the book?

My excel used the old constant values before and I only change it with the new value in 3rd edition, so i didn't change the way to calculate.

below is my excel :
Attached Files: 1. Scan for viruses before opening, 2. Please report any 'bad' files by Reporting this post, 3. Use at your Own Risk.
 General MSA Report.xls (73.5 KB, 1111 views)
 Thanks to Alex.G for your informative Post and/or Attachment!

Post Number #10
12th December 2007, 10:37 PM
 Yew Jin Total Posts: 196
Re: How to determine the values of k1, k2, k3 in Gage R&R

I came to this question few years ago and had done some further study on them.......We need to use the Appendix C - d2 table for K constants calculation.

K1 - Used for Repeatability, Equipment Variation (EV) calculation
Find the d2 from Appendix C - d2 table,
focus on the subgroup size(m) for number of trials we used in GR&R study, number of subgroups (g) for parts x number of operators we used in GR&R study. If the parts x number of operator greater then 20, find the d2 at the bottom of the table.
K1 = 1/d2

K2 - Used for Reproducibility, Appraiser Variation (AV) calculation
Find the d2 from Appendix C - d2 table,
focus on the subgroup size(m) for number of operators we used in GR&R study, number of subgroups (g) is set as 1 as there is only one range calculation in this study.
K2 = 1/d2

K3 - Used for Part Variation (PV) calculation
Find the d2 from Appendix C - d2 table,
focus on the subgroup size(m) for number of samples we used in GR&R study, number of subgroups (g) is set as 1 as there is only one range calculation in this study.
K3 = 1/d2

AIAG MSA guideline used formula K = 1/d2, all the sigma (EV, AV and PV) calculated used the original formula with K value replaced and %PT Ratio = (100x 5.15 x sigma R&R)/product specification.

Larry B. Barrentine used formula K = 5.15/d2, all the sigma (EV, AV and PV) calculated used the original formula with K value replaced BUT divided by 5.15 backand %PT Ratio = (100 x 5.15 x sigma R&R)/product specification.

Noted: We do not use the factor 5.15 or 6 in GR&R% calculation (compare to process variation), it is only apply in PT Ratio calculation (compare to product specification)
 Thank You to Yew Jin for your informative Post and/or Attachment!
Post Number #11
12th December 2007, 11:05 PM
 Miner Total Posts: 4,228
Re: How to determine the values of k1, k2, k3 in Gage R&R

Yew Jin is exactly correct. MSA 2nd ed used 5.15 in the formula, and 3rd ed simplified the formula by removing it and using the new constants.
Post Number #12
13th December 2007, 01:04 AM
 Alex.G Total Posts: 9
Re: How to determine the values of k1, k2, k3 in Gage R&R

So if I understand, my excel sheet was wrong before because we used the constant K without dividing by 5.15, now it should be ok.
I tried with the value from MSA reference manual 3rd edition example p113 and I get the same result.
So means my excel is good, right?
Someone can fastly review it for me to confirm ?

thanks a lot
Post Number #13
13th December 2007, 09:49 AM
 antoine.dias Total Posts: 530
Re: How to determine the values of k1, k2, k3 in Gage R&R

The problem is not in your Excel.

If you compare the 2nd version results with the 3rd version there is no significant difference when calculating in relation to the total variation TV.

The problem starts when you calculate in relation to the tolerance.
In version 2 you can (have to) use the tolerance width, in version 3 you have to divide the tolerance by 6 ( See page 116 in the MSA manual )

Hope this helps,

Best regards,

Antoine
 Thanks to antoine.dias for your informative Post and/or Attachment!
Post Number #14
13th December 2007, 09:09 PM
 Alex.G Total Posts: 9
Re: How to determine the values of k1, k2, k3 in Gage R&R

ok i found it :

TV = 5.15 (process variation/6) in 2nd edition

and TV =process variation/6 in 3rd edition,

So that mean I have to divide TV = sqrt(GRR^2+PV^2) by 5.15, right?

thanks everybody I think I will have a perfect excelsheet soon,
Post Number #15
13th December 2007, 10:19 PM
 Alex.G Total Posts: 9
Re: How to determine the values of k1, k2, k3 in Gage R&R

I read again the book and if I understand, it is only in the case, my analysis is based on the tolerance I have to divided by 6. In my case it is on Total variation, There is something I can't understand, if the form in the 2nd edition is based on total variation and 3rd edition too, i don't have to change the excel sheet except for the constant. but change the constant change considerably the result.
That drive me crazy
Some one can please review fastly my excel.

--> I noticed if I replace in my excel the value from 3rd edition p113, I obtain the result from p114 of 3rd edition, so my excel is good?

Thanks for your help
Post Number #16
14th December 2007, 01:42 AM
 Atul Khandekar Total Posts: 1,457
Re: How to determine the values of k1, k2, k3 in Gage R&R

Alex, I quickly scanned your Excel sheet, there doesn't seem to be anything wrong with this.

As regards %Tol, IMO, there should not be a very BIG difference between 2nd and 3rd editions.

The 2nd edition directly calculated the value of the "Full spread" of GRR error, which was 5.15* GRR_Standard_Deviation. %Tolerance = Tolerance / (Full GRR) = (Tol)/(5.15*GRR_Stdev) = (Tol/5.15) / (GRR_Stdev)

In the third edition we calculate Standard_deviation of GRR (and also EV,AV, TV,PV etc). % Tol = Tolerance / (Full GRR), where full GRR spread is 6*GRR_StDev. This is the same as (Tol)/(6*GRR_Stdev) = (Tol/6) / (GRR_Stdev)

The difference in %Tol will only be to the extent of using 6 in place of 5.15.
 Thanks to Atul Khandekar for your informative Post and/or Attachment!

 The Elsmar Cove Business Systems and Standards Discussion Forums How to determine the values of k1, k2, k3 in Gage R&R

 Bookmarks

 Visitors Currently Viewing this Thread: 1 (0 Registered Visitors (Members) and 1 Unregistered Guest Visitors)
 Thread Tools Search this Thread Search this Thread: Advanced Forum Search Display Modes Rate Thread Content Linear Mode Rate Thread Content: 5 : Excellent 4 : Good 3 : Average 2 : Bad 1 : Terrible

 Forum Posting Settings You may not post new threads You may not post replies You may not post attachments You may not edit your posts BB code is On Emoticons are On [IMG] code is On HTML code is Off Forum Rules

 Similar Discussion Threads Discussion Thread Title Thread Starter Forum Replies Last Post or Poll Vote amiuda General Measurement Device and Calibration Topics 4 25th April 2013 12:22 AM Howard Atkins Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 11 3rd June 2011 04:18 PM gregb Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 1 28th June 2006 02:57 AM Star18 Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 5 2nd February 2006 03:09 PM dbulak Capability, Accuracy and Stability - Processes, Machines, etc. 4 12th January 2004 11:25 AM

The time now is 12:15 PM. All times are GMT -4.
Your time zone can be changed in your UserCP --> Options.